{"c898cef85a73148a11d8282302c4d9a8m.herschel":{"DOI":"10.48786/edbt.2023.07","ISBN":"","ISSN":"","URL":"https://doi.org/10.48786/edbt.2023.07","abstract":"","annote":"","author":[{"family":"Gazzarri","given":"Leonardo"},{"family":"Herschel","given":"Melanie"}],"citation-label":"DBLP:conf/edbt/GazzarriH23","collection-editor":[],"collection-title":"","container-author":[],"container-title":"International Conference on Extending Database Technology (EDBT)","documents":[],"edition":"","editor":[],"event-date":{"date-parts":[["2023"]],"literal":"2023"},"event-place":"","id":"c898cef85a73148a11d8282302c4d9a8m.herschel","interhash":"c9dff3c29fe8c95c9aab8edff5386717","intrahash":"c898cef85a73148a11d8282302c4d9a8","issue":"","issued":{"date-parts":[["2023"]],"literal":"2023"},"keyword":"intcdc entity-resolution peer rp9-2 ipvs-de","misc":{"bibsource":"dblp computer science bibliography, https://dblp.org","doi":"10.48786/edbt.2023.07"},"note":"","number":"","number-of-pages":"11","page":"80--91","page-first":"80","publisher":"","publisher-place":"","status":"","title":"Progressive Entity Resolution over Incremental Data","type":"paper-conference","username":"m.herschel","version":"","volume":""},"ca69630dc2a3e12b6e51002044208101m.herschel":{"DOI":"","ISBN":"","ISSN":"","URL":"https://www.ipvs.uni-stuttgart.de/departments/de/resources/papers/ER_icde_2021.pdf","abstract":"","annote":"","author":[{"family":"Gazzarri","given":"Leonardo"},{"family":"Herschel","given":"Melanie"}],"citation-label":"gazzarri2021endtoend","collection-editor":[],"collection-title":"","container-author":[],"container-title":"Proceedings of the IEEE International Conference on Data Engineering (ICDE)","documents":[],"edition":"","editor":[],"event-date":{"date-parts":[["2021"]],"literal":"2021"},"event-place":"","id":"ca69630dc2a3e12b6e51002044208101m.herschel","interhash":"0d963729256107fd539182a1b9813dd3","intrahash":"ca69630dc2a3e12b6e51002044208101","issue":"","issued":{"date-parts":[["2021"]],"literal":"2021"},"keyword":"entity-resolution peer ipvs-de rp9","note":"","number":"","page":"","page-first":"","publisher":"","publisher-place":"","status":"","title":"End-to-end Task Based Parallelization for Entity Resolution on Dynamic Data","type":"paper-conference","username":"m.herschel","version":"","volume":""},"29d6bb73e60811cf405472f2dd4f93a3m.herschel":{"DOI":"10.1007/s00450-019-00409-6","ISBN":"2524-8529","ISSN":"","URL":"https://doi.org/10.1007/s00450-019-00409-6","abstract":"Entity resolution (ER) refers to the problem of finding which virtual representations in one or more data sources refer to the same real-world entity. A central question in ER is how to find matching entity representations (so called duplicates) efficiently and in a scalable way. One general technique to address these issues is to leverage parallelization. In particular, almost all work on parallel ER focus on data parallelism. This paper focuses on task parallelism for ER. This type of parallelism allows to support incremental ER that offers incremental computation of the solution by streaming results of intermediate stages of ER as soon as they are computed. This possibly allows to obtain results in a more timely fashion and can also serve in a service-oriented setting with limited time or monetary budget. In summary, this paper presents a framework for task-parallelization of ER, supporting in particular ER of large amounts of semi-structured and heterogeneous data. We also discuss a possible implementation of our framework.","annote":"","author":[{"family":"Gazzarri","given":"Leonardo"},{"family":"Herschel","given":"Melanie"}],"citation-label":"cite-key","collection-editor":[],"collection-title":"","container-author":[],"container-title":"SICS Software-Intensive Cyber-Physical Systems","documents":[],"edition":"","editor":[],"event-date":{"date-parts":[["2020"]],"literal":"2020"},"event-place":"","id":"29d6bb73e60811cf405472f2dd4f93a3m.herschel","interhash":"fb5c8b580d9e500b27de194b5101e6f3","intrahash":"29d6bb73e60811cf405472f2dd4f93a3","issue":"1","issued":{"date-parts":[["2020"]],"literal":"2020"},"keyword":"entity-resolution ipvs-de","misc":{"ty":"JOUR","isbn":"2524-8529","bdsk-url-1":"https://doi.org/10.1007/s00450-019-00409-6","date-added":"2020-07-01 13:28:59 +0800","date-modified":"2020-07-01 13:28:59 +0800","id":"Gazzarri2019","da":"2019/08/26","doi":"10.1007/s00450-019-00409-6"},"note":"","number":"1","number-of-pages":"7","page":"31-38","page-first":"31","publisher":"","publisher-place":"","status":"","title":"Towards task-based parallelization for entity resolution","type":"article-journal","username":"m.herschel","version":"","volume":"35"},"eeec6210a444148a590e9c5d95ac43c1m.herschel":{"DOI":"10.5441/002/edbt.2020.47","ISBN":"","ISSN":"","URL":"","abstract":"","annote":"","author":[{"family":"Gazzarri","given":"Leonardo"},{"family":"Herschel","given":"Melanie"}],"citation-label":"DBLP:conf/edbt/GazzarriH20","collection-editor":[],"collection-title":"","container-author":[],"container-title":"Proceedings of the International Conference on Extending Database Technology (EDBT)","documents":[],"edition":"","editor":[],"event-date":{"date-parts":[["2020"]],"literal":"2020"},"event-place":"","id":"eeec6210a444148a590e9c5d95ac43c1m.herschel","interhash":"439202f9f04450219a91335b56b06b12","intrahash":"eeec6210a444148a590e9c5d95ac43c1","issue":"","issued":{"date-parts":[["2020"]],"literal":"2020"},"keyword":"entity-resolution ipvs-de","misc":{"doi":"10.5441/002/edbt.2020.47"},"note":"","number":"","number-of-pages":"3","page":"419--422","page-first":"419","publisher":"OpenProceedings.org","publisher-place":"","status":"","title":"Boosting Blocking Performance in Entity Resolution Pipelines: Comparison Cleaning using Bloom Filters","type":"paper-conference","username":"m.herschel","version":"","volume":""}}